Bluetooth-based context modeling
Eric Vance, Ani Nahapetian · 2018
In this work, we explore the feasibility of using only the Bluetooth received signal strength of a smart device to infer its user context. Devices that use Bluetooth wireless communication constantly transmit their wireless signal, especially in the case of smart watches that communicate via Bluetooth with their paired smart phones for their most basic functions. Adversaries or non-malicious applications can monitor Bluetooth signal strength to extrapolate the activities in which a user is engaged and the location of certain devices (e.g. cellphone in pocket or on a desk). We experimentally evaluate the accuracy with which a range of activities, including walking, typing, writing, and using a mouse, can be differentiated, simply by using the RSSI of a user-worn smart watch.